English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  An Expectation Maximization Algorithm for Continuous Markov Decision Processes with Arbitrary Reward

Hoffman, M., Freitas, N., Doucet, A., & Peters, J. (2009). An Expectation Maximization Algorithm for Continuous Markov Decision Processes with Arbitrary Reward. In D. Van Dyk, & M. Welling (Eds.), Twelfth International Conference on Artificial Intelligence and Statistics (AIStats 2009) (pp. 232-239). Cambridge, MA, USA: MIT Press.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C53B-E Version Permalink: https://hdl.handle.net/21.11116/0000-0002-FE36-4
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
http://proceedings.mlr.press/v5/hoffman09a/hoffman09a.pdf (Publisher version)
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Hoffman, M, Author
Freitas , ND, Author
Doucet, A, Author
Peters, J1, 2, Author           
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: We derive a new expectation maximization algorithm for policy optimization in linear Gaussian Markov decision processes, where the reward function is parameterised in terms of a flexible mixture of Gaussians. This approach exploits both analytical tractability and numerical optimization. Consequently, on the one hand, it is more flexible and general than closed-form solutions, such as the widely used linear quadratic Gaussian (LQG) controllers. On the other hand, it is more accurate and faster than optimization methods that rely on approximation and simulation. Partial analytical solutions (though costly) eliminate the need for simulation and, hence, avoid approximation error. The experiments will show that for the same cost of computation, policy optimization methods that rely on analytical tractability have higher value than the ones that rely on simulation.

Details

show
hide
Language(s):
 Dates: 2009-04
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: URI: http://jmlr.csail.mit.edu/proceedings/papers/v5/hoffman09a.html
BibTex Citekey: 5658
 Degree: -

Event

show
hide
Title: Twelfth International Conference on Artificial Intelligence and Statistics (AIStats 2009)
Place of Event: Clearwater Beach, FL, USA
Start-/End Date: 2009-04-16 - 2009-04-18

Legal Case

show

Project information

show

Source 1

show
hide
Title: Twelfth International Conference on Artificial Intelligence and Statistics (AIStats 2009)
Source Genre: Proceedings
 Creator(s):
Van Dyk, D, Editor
Welling, M, Editor
Affiliations:
-
Publ. Info: Cambridge, MA, USA : MIT Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 232 - 239 Identifier: -

Source 2

show
hide
Title: JMLR Workshop and Conference Proceedings
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 5 Sequence Number: - Start / End Page: - Identifier: -